FAMA: The First Large-Scale Open-Science Speech Foundation Model for English and Italian

The development of speech foundation models (SFMs) like Whisper and SeamlessM4T has significantly advanced the field of speech processing. However, their closed nature–with inaccessible training data and code–poses major reproducibility and fair evaluation challenges. While other domains have made substantial progress toward open science by developing fully transparent models trained on open-source (OS) code and data, similar efforts in speech processing remain limited. To fill this gap, weintroduceFAMA,thefirstfamilyofopenscienceSFMsforEnglishandItalian, trainedon150k+hoursofOSspeechdata. Moreover, we present a new dataset containing 16k hours of cleaned and pseudo-labeled speech for both languages. Results show that FAMA achieves competitive performance compared to existing SFMs while being up to 8 times faster. All artifacts, including codebase, datasets, and models, are released under OS-compliant licenses, promoting openness in speech technology research. The FAMA collection is available at: https://huggingface.co/collections/FBK-MT/fama-683425df3fb2b3171e0cdc9e